arXiv cs.AI· Haichuan Tan, Bowen Gao, Tao Huang, Jiaxin Tan, Xin Hong, Baoguo Yao, Yifei Wang, Zhichao Deng, Hanji Du, Dapeng Jiang, Yiheng Li, Weiwei Ma, Xin Ma, Yuqi Shi, Zixiang Wang, Kelin Wu, Tianxiang Wu, Wenxuan Xie, Jie Zang, Huiyu Zhang, Mojia Zhang, Yuying Zhang, Ya-Qin Zhang, Wei-Ying Ma, Yanyan Lan·· 11 小时前AI 评分58
PharmAgents2：面向自主端到端药物发现的智能体系统
PharmAgents2: Towards Autonomous End-to-End Drug Discovery
AI 导读
PharmAgents2 是一个面向端到端药物发现的自主系统，结合知识增强决策与可扩展的大规模探索。其 Paper2Skill 从公开来源提取可迁移的科学决策知识，Self-Scaling Discovery 则通过继承研究上下文与决策能力的并行智能体扩展探索。
正文 · 原文
Authors:Haichuan Tan, Bowen Gao, Tao Huang, Jiaxin Tan, Xin Hong, Baoguo Yao, Yifei Wang, Zhichao Deng, Hanji Du, Dapeng Jiang, Yiheng Li, Weiwei Ma, Xin Ma, Yuqi Shi, Zixiang Wang, Kelin Wu, Tianxiang Wu, Wenxuan Xie, Jie Zang, Huiyu Zhang, Mojia Zhang, Yuying Zhang, Ya-Qin Zhang, Wei-Ying Ma, Yanyan Lan
Abstract:Drug discovery requires continuous scientific decision-making across a vast research space. We introduce PharmAgents2, an autonomous system for end-to-end drug discovery that combines knowledge-enhanced decision-making with organized large-scale exploration. Paper2Skill extracts transferable scientific decision knowledge from public sources and, together with expert-developed skills, supports research decisions. Self-Scaling Discovery expands exploration through parallel agents inheriting research context and decision-making capabilities across targets, scientific hypotheses, and discovery strategies. We introduce PharmAgents-Bench v0.1, comprising 121 questions across nine decision scenarios and three end-to-end tasks assessed with expert-defined process rubrics. PharmAgents2 outperforms evaluated baselines in most decision categories and achieves the highest process scores on all three end-to-end tasks. In three real-world studies, autonomous investigations generated findings subsequently supported by human-executed experiments. For LpxH, PharmAgents2 hypothesized a previously unreported allosteric site and screened compounds against it, identifying a novel inhibitor scaffold with experimentally confirmed inhibitory activity and binding. For JAK1, it prioritized a covalent inhibition strategy and nominated compounds with experimentally demonstrated activity. Starting from a known bioactive molecule, Self-Scaling Discovery explored candidate targets across the proteome and identified a new binding target, with the interaction subsequently confirmed experimentally. PharmAgents2 represents a prototype of a virtual pharmaceutical company, marking a step toward autonomous end-to-end drug discovery.
| Subjects: | Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM) |
| Cite as: | arXiv:2611.07653 [cs.AI] |
| (or arXiv:2611.07653v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07653 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haichuan Tan [view email]
[v1]
Thu, 5 Nov 2026 08:39:19 UTC (19,231 KB)
来源：arXiv cs.AI · arxiv.org